## TL;DR
Fix this in synthetic data agent workflow by acting on the exact message first: parse the Great Expectations results file with a JSON reader and check the success flag per expectation rather than scanning summary text, list every failed expectation by column and rule in the agent report, and cross check the count of failed expectations against the suite summary count before signing off. Do not rerun the whole job unchanged, because the same inputs produce the same failure. Prove the fix on one table, batch or record set first, then rerun the full scope and reconcile the counts.

```text
agent failed parsing Great Expectations results - synthetic failures reported as passes
```

## Use this when
- The operation in synthetic data agent workflow fails with this exact message or symptom: agent failed parsing Great Expectations results - synthetic failures reported as passes.
- The same failure repeats on retry with unchanged inputs.
- Generation, validation or export is blocked until this item completes.

## Not for this skill when
- The message is an outage notice from the platform. Resolve that first, then return here if this error remains.
- The operation completes and you only disagree with its output quality. That is a quality review, not this failure.

## Steps
1. Reproduce the failure with the smallest scope that still shows it in synthetic data agent workflow, and copy the full message plus the table, column or job involved into the run notes. Verify: the error is reproduced on demand with a named scope, not only seen in a log.
2. Apply the specific fix for this error: parse the Great Expectations results file with a JSON reader and check the success flag per expectation rather than scanning summary text, list every failed expectation by column and rule in the agent report, and cross check the count of failed expectations against the suite summary count before signing off. Verify: the smallest failing scope now completes, or the named column, table or job behaves as the fix predicts.
3. Check the neighbouring tables, columns or jobs that share the same config, schema or credential, because this class of failure rarely affects only one item. Verify: the neighbouring items are listed and each is marked affected or clear.
4. Rerun the original operation in synthetic data agent workflow on the previously failing scope, watching for the same message rather than assuming success from a quiet log. Verify: the operation completes and the original message does not appear.
5. Compare the result counts, distributions or status against the source in synthetic data agent workflow so a silent partial success is caught before sign off. Verify: counts match the source or every difference is named and explained.
6. Record the fix, the triggering input and the verification result on the item so the next occurrence is recognised immediately. Verify: the record names the error, the fix applied and the evidence of success.

## Why it happens
Expectation result files nest per expectation verdicts under summary statistics, and reading only the headline or a text scan inverts the result when most expectations pass but the important ones fail.

## Variant phrasings

### agent failed parsing Great Expectations results - synthetic failures reported as passes
The verbatim form searchers paste from the terminal or console. Treat it identically: same fix, same single scope proof, then the full rerun.

### How to fix - agent failed parsing Great Expectations results synthetic failures reported as passes
The how-to phrasing for the same failure in synthetic data agent workflow. The steps above apply unchanged; start at the reproduction step rather than skipping to the rerun.

### synthetic data agent workflow troubleshooting for this failure
The symptom-first phrasing used when the console hides the full message. Surface the full message first, confirm it matches the code block above, then follow the steps.

Compatibility: synthetic data agent workflow at current versions, plus the platform API or console the query names; no extra tooling beyond the source system access needed to verify counts.

## Provenance

Resolved from the public thread: https://vectle.com/posts/pst_dBfEuyESp4uIpkFwfIN8xw